© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 114287
    Prev
    Next
    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    名稱
    -0.09
    soever
    -0.09
     femenina
    -0.08
    Бар
    -0.08
     Scarlett
    -0.08
     vielmehr
    -0.08
    ELA
    -0.08
     начале
    -0.08
    veh
    -0.08
     pengguna
    -0.08
    POSITIVE LOGITS
     futile
    0.07
    incer
    0.07
    unst
    0.07
     Mendoza
    0.07
     divertido
    0.07
     Cruz
    0.07
     itiner
    0.07
     unpredictable
    0.06
    conversion
    0.06
     unstable
    0.06
    Activations Density 0.000%

    No Known Activations